Getting started

You should be running your first prompt in under two minutes.

1. Install the desktop app

The client is a signed Electron build for macOS, Windows, and Linux. Grab the latest from the download page.

All builds are code-signed. On first launch, macOS will prompt you to allow network access — that's the app fetching the NLP engine address.

2. Create an API key

You need a key to authenticate against the NLP engine. Create one from your dashboard's Keys page. Keys are scoped per device — you can revoke one without invalidating the others.

iom_8f4c...     ← copy this once; it's shown only at creation time

Paste it into the client's Keys screen.

3. Connect a database or spreadsheet

Click Connect on the home screen to add a connection or drag & drop a spreadsheet. Insight O' Mate supports MongoDB, Redis, Firestore, DynamoDB, and Excel/CSV Spreadsheets — pick the type, paste a connection string, or select a file. The client stores database credentials encrypted in your OS keychain (macOS Keychain, Windows Credential Manager, or libsecret on Linux) — never on disk as plaintext.

A read-only role is strongly recommended. The example below uses MongoDB; see Connecting databases for the minimal Atlas / self-hosted role definitions.

4. Ask a question

Type a question in plain English:

Show me users who signed up last week and have more than 2 orders.

Insight O' Mate will:

1. Inspect the schema of your users and orders collections
2. Send (prompt + schema) to the stateless NLP engine
3. Receive a structured intent object (AST) back
4. Translate that intent into a pipeline like db.users.aggregate([{ $match: ... }, { $lookup: ... }]) locally inside the desktop sidecar
5. Run the query locally against your database and render the result table

You can click the Query history button in the top navigation at any time to see your past runs.

What to read next

• If the prompt produced the wrong query, skim the Privacy model — it explains what the engine sees and doesn't, which helps you phrase prompts more precisely.